Filter Cryillic file from the folder in python

	"" DetectCyrillic file search content in file recursiverly and filters all the files
	having Cyrillic character in it preserving the folder structure.
	Supported files: Docx Pptx Xlsx txt
	Instruction to use:
	This script expects user to provide following information through command line argument
	1) Source directory where the file will be searched.
	2) Target directory where the matched result will be copied.
	Note: This script expects that no two file have same name and extension ,
	they will be replaced in target directory otherwise
	Eg to run the code
	Python DetectCyrillic.py sourceFolder targetFolder
	"""
	import os
	import sys
	from shutil import copy
	import logging
	import docx2txt
	import fulltext
	import re
	from colorama import Fore, init
	init()
	logger = logging.getLogger(__name__)
	logging.basicConfig(stream=sys.stderr, level=logging.INFO)
	def has_cyrillic(text):
	return bool(re.search('[\u0400-\u04FF]', text))
	def copyErrorFiles(file, dest) :
	""" Copies files to the Error folder if unable to parse the document
	"""
	if not os.path.isdir(dest):
	os.makedirs(dest)
	listDir = os.listdir(dest)
	finalDir = os.path.join(dest, "Error")
	if "Error" in listDir:
	copy(file, finalDir)
	else:
	os.makedirs(finalDir)
	copy(file, finalDir)
	def processTxtfile(file,dest):
	"""
	Process text file and returns true if file contains cyrillic character. """ try:
	with open(file, encoding="utf-8", errors='ignore') as f:
	for line in f:
	russian = has_cyrillic(line)
	if russian:
	return True return False
	except Exception as e:
	print(Fore.RED +"cannot process txt file %s" % file)
	copyErrorFiles(file, dest)
	def processDocxfile(file,dest):
	"
	Process docx file and returns true if file contains cyrillic character. """
	try:
	doc = docx2txt.process(file)
	russian = has_cyrillic(doc)
	return russian
	except Exception as e:
	print(Fore.RED +"cannot process docx file %s" % file)
	copyErrorFiles(file, dest)
	def processPptxfile(file,dest):
	"""
	Process pptx file and returns true if file contains cyrillic character. """
	try:
	doc = fulltext.get(file, encoding="utf-8", errors='ignore')
	russian = has_cyrillic(doc)
	return russian
	except Exception as e:
	print(Fore.RED +"cannot process pptx file %s" % file)
	copyErrorFiles(file, dest)
	def processExcelfile(file,dest):
	"""
	Process xlsx file and returns true if file contains cyrillic character. """
	try:
	doc = fulltext.get(file, encoding="utf-8", errors='ignore')
	russian = has_cyrillic(doc)
	return russian
	except Exception as e:
	print(Fore.RED +"cannot process file %s" % file)
	copyErrorFiles(file, dest)
	def detectCyrillic(file,dest):
	ext = (file.split(".")[-1]).lower()
	if ext == "txt":
	lang = processTxtfile(file, dest)
	elif ext == "docx":
	lang = processDocxfile(file, dest)
	elif ext == "pptx":
	lang = processPptxfile(file, dest)
	elif ext == "xlsx":
	lang = processExcelfile(file, dest)
	else :
	print(Fore.RED + "Invalid Extension %s " % (ext))
	copyErrorFiles(file, dest)
	lang = False return lang
	def findAll(src,dest):
	for root, dirs, files in os.walk(src):
	for x in files:
	print(Fore.WHITE + "Start : Detect Cryllic %s " %(x))
	srcfilePath = os.path.join(root, x)
	rootdest = root.replace(src, dest)
	langSet = detectCyrillic(srcfilePath,rootdest)
	if langSet:
	if os.path.isdir(rootdest):
	copy(srcfilePath, rootdest)
	else :
	os.makedirs(rootdest)
	copy(srcfilePath, rootdest)
	print(Fore.WHITE + "End : %s " % (x))
	if __name__ == "__main__":
	findAll(sys.argv[1], sys.argv[2])

view raw detect_cryillic.py hosted with ❤ by GitHub